commit 640488bab16dffcad873c6a59c644d640148b39d parent b07234e8ee6a45da2ac450dbd3454c035c0b44c0 Author: Wei Tang <hi@that.world> Date: Tue, 24 Jan 2017 14:17:02 +0800 Handle Chinese Hanzi, Hiragana and Katakana in tag Diffstat:
| M | scribble-lib/scribble/base.rkt | | | 7 | ++++++- |
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/scribble-lib/scribble/base.rkt b/scribble-lib/scribble/base.rkt @@ -44,7 +44,12 @@ (define (gen-tag content) (datum-intern-literal - (regexp-replace* "[^-a-zA-Z0-9_=]" (content->string content) "_"))) + ;; Generate tag from ASCII plus CJK characters. Constraining to + ;; ASCII for most purposes helps avoid encoding issues for + ;; uncooperative environments, but constraining to ASCII is too + ;; uncooperative in another direction for CJK text (i.e., creates + ;; too many conflicting tags). + (regexp-replace* #px"[^-a-zA-Z0-9_=\u4e00-\u9fff\u3040-\u309F\u30A0-\u30FF]" (content->string content) "_"))) (define (prefix->string p) (and p (if (string? p)